llvm/unittests/Support/ConvertEBCDICTest.cpp

   1 //===- unittests/Support/ConvertEBCDICTest.cpp - EBCDIC/UTF8 conversion tests
   2 //-===//
   3 //
   4 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
   5 // See https://llvm.org/LICENSE.txt for license information.
   6 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
   7 //
   8 //===--------------------------------------------------------------------------===//
   9
  10 #include "llvm/Support/ConvertEBCDIC.h"
  11 #include "llvm/ADT/SmallString.h"
  12 #include "gtest/gtest.h"
  13 using namespace llvm;
  14
  15 namespace {
  16
  17 // String "Hello World!"
  18 static const char HelloA[] =
  19     "\x48\x65\x6C\x6C\x6F\x20\x57\x6F\x72\x6C\x64\x21\x0a";
  20 static const char HelloE[] =
  21     "\xC8\x85\x93\x93\x96\x40\xE6\x96\x99\x93\x84\x5A\x15";
  22
  23 // String "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
  24 static const char ABCStrA[] =
  25     "\x41\x42\x43\x44\x45\x46\x47\x48\x49\x4A\x4B\x4C\x4D\x4E\x4F\x50\x51\x52"
  26     "\x53\x54\x55\x56\x57\x58\x59\x5A\x61\x62\x63\x64\x65\x66\x67\x68\x69\x6A"
  27     "\x6B\x6C\x6D\x6E\x6F\x70\x71\x72\x73\x74\x75\x76\x77\x78\x79\x7A";
  28 static const char ABCStrE[] =
  29     "\xC1\xC2\xC3\xC4\xC5\xC6\xC7\xC8\xC9\xD1\xD2\xD3\xD4\xD5\xD6\xD7\xD8\xD9"
  30     "\xE2\xE3\xE4\xE5\xE6\xE7\xE8\xE9\x81\x82\x83\x84\x85\x86\x87\x88\x89\x91"
  31     "\x92\x93\x94\x95\x96\x97\x98\x99\xA2\xA3\xA4\xA5\xA6\xA7\xA8\xA9";
  32
  33 // String "¡¢£AÄÅÆEÈÉÊaàáâãäeèéêë"
  34 static const char AccentUTF[] =
  35     "\xc2\xa1\xc2\xa2\xc2\xa3\x41\xc3\x84\xc3\x85\xc3\x86\x45\xc3\x88\xc3\x89"
  36     "\xc3\x8a\x61\xc3\xa0\xc3\xa1\xc3\xa2\xc3\xa3\xc3\xa4\x65\xc3\xa8\xc3\xa9"
  37     "\xc3\xaa\xc3\xab";
  38 static const char AccentE[] = "\xaa\x4a\xb1\xc1\x63\x67\x9e\xc5\x74\x71\x72"
  39                               "\x81\x44\x45\x42\x46\x43\x85\x54\x51\x52\x53";
  40
  41 // String with Cyrillic character ya.
  42 static const char CyrillicUTF[] = "\xd0\xaf";
  43
  44 TEST(CharSet, FromUTF8) {
  45   // Hello string.
  46   StringRef Src(HelloA);
  47   SmallString<64> Dst;
  48
  49   std::error_code EC = ConverterEBCDIC::convertToEBCDIC(Src, Dst);
  50   EXPECT_TRUE(!EC);
  51   EXPECT_STREQ(HelloE, static_cast<std::string>(Dst).c_str());
  52   Dst.clear();
  53
  54   // ABC string.
  55   Src = ABCStrA;
  56   EC = ConverterEBCDIC::convertToEBCDIC(Src, Dst);
  57   EXPECT_TRUE(!EC);
  58   EXPECT_STREQ(ABCStrE, static_cast<std::string>(Dst).c_str());
  59   Dst.clear();
  60
  61   // Accent string.
  62   Src = AccentUTF;
  63   EC = ConverterEBCDIC::convertToEBCDIC(Src, Dst);
  64   EXPECT_TRUE(!EC);
  65   EXPECT_STREQ(AccentE, static_cast<std::string>(Dst).c_str());
  66   Dst.clear();
  67
  68   // Cyrillic string. Results in error because not representable in 1047.
  69   Src = CyrillicUTF;
  70   EC = ConverterEBCDIC::convertToEBCDIC(Src, Dst);
  71   EXPECT_EQ(EC, std::errc::illegal_byte_sequence);
  72   Dst.clear();
  73 }
  74
  75 TEST(CharSet, ToUTF8) {
  76   // Hello string.
  77   StringRef Src(HelloE);
  78   SmallString<64> Dst;
  79
  80   ConverterEBCDIC::convertToUTF8(Src, Dst);
  81   EXPECT_STREQ(HelloA, static_cast<std::string>(Dst).c_str());
  82   Dst.clear();
  83
  84   // ABC string.
  85   Src = ABCStrE;
  86   ConverterEBCDIC::convertToUTF8(Src, Dst);
  87   EXPECT_STREQ(ABCStrA, static_cast<std::string>(Dst).c_str());
  88   Dst.clear();
  89
  90   // Accent string.
  91   Src = AccentE;
  92   ConverterEBCDIC::convertToUTF8(Src, Dst);
  93   EXPECT_STREQ(AccentUTF, static_cast<std::string>(Dst).c_str());
  94   Dst.clear();
  95 }
  96
  97 } // namespace